The NLCD 2001 is created by partitioning the U.S. into mapping zones. A total of 66 mapping zones were delineated within the conterminous U.S. based on ecoregion and geographical characteristics, edge matching features and the size requirement of Landsat mosaics. Mapping zone 32 encompasses whole or portions of several states, including the states of Texas, Oklahoma, and Kansas. Questions about the NLCD mapping zone 32 can be directed to the NLCD 2001 land cover mapping team at the USGS/EROS, Sioux Falls, SD (605) 594-6151 or mrlc@usgs.gov.
Conceptually, the descriptive tree is a classification tree generated by using the final minimum-map- unit land cover product (1 acre) as training data, and Landsat and other ancillary data as predictors. The goal of the descriptive tree is to summarize the effects of boosted trees (10 sequential classification trees) into a single condensed decision tree that can be used as a diagnostic tool for the classification process. This descriptive tree can be used to assess the relative importance of each of the input data sets on each land cover class. Such information may also be useful to customize the minimum-mapping-unit classification to meet a user's specific needs through raster modeling. Descriptive trees usually capture 60 to 80% of the information from the original land cover data.
The leaf or terminal nodes of the descriptive tree are assigned to sequential numbers (called node numbers) and mapped across the entire mapping zone on a pixel-by-pixel basis. These node numbers can then be matched with the various conditional statements associated with each respective terminal node. This spatial layer appears similar to a cluster map, but is the result of a supervised classification - not an unsupervised clustering. This node map can potentially be used as input by users to customize NLCD land cover, by linking the spatial extent of an individual node with the rules of the conditional statement.
The Land Cover spatial classification confidence data layer is provided to users to help determine the per-pixel spatial confidence of the NLCD 2001 land cover prediction from the descriptive tree. The C5 algorithm produces an estimate (a value between 0% and 100%) that indicates the confidence of rule predictions at each node based on the training data. This spatial confidence map should be considered as only one indicator of relative reliability of the land cover classification, rather than a precise estimate. Users should be aware that this estimate is made based on only training data, and is derived from a generalized descriptive decision tree that reproduces the final land cover data. However, this layer provides valuable insight for a user to determine the risk or confidence they choose to place in each pixel of land cover.
A logic statement from a descriptive tree classification describes each classification rule for each classified pixel. An example of the logic statement follows:
IF tasseled-cap wetness > 140 and imperviousness = 0 and canopy density < 4, then classify as Water
This logic file can be used in combination with the spatial node map to identify classification logic and allow modifications of the classification based on user's knowledge and/or additional data sets.
Additional information may be found at <http://www.mrlc.gov/mrlc2k_nlcd.asp>.
To conduct the land cover classification using DT, a large quantity of training data is required. For mapping zone 32 training data were collected from several combined sources including ancillary land cover maps such as USGS Multi-resolution Land Cover (MRLC) 1992 maps for Texas, Oklahoma, and Kansas, GAP Regional Land Cover maps for Oklahoma and Kansas, numerous USGS Digital Orthophoto Quarter Quadrangles (DOQQs), and 2004 CIR DOQQs from the USDA National Agricultural Imagery Program (NAIP). Land cover classes from ancillary land cover map datasets were cross-walked to NLCD 2001 equivalent classification codes prior to use. A unique source image for random sampling of training points was created from multiple datasets (two or more) to take advantage of previous land cover mapping efforts. ERDAS Imagine models were designed to intersect map images to determine the spatial extent of areas where two or more existing maps agreed on the land cover classification. Classes were randomly sampled on an individual basis in a proportion roughly approximating the percentage of pixels of the sample class in the training image.
Note that the training data were used to map all land cover classes except for four classes in urban and sub-urban areas (developed open space, low intensity developed, medium intensity developed, high intensity developed). All urban and suburban land cover classes were mapped and quality assessed separately through a sub-pixel quantification of impervious surfaces using a regression tree modeling method.
Following the development of the best classification through decision tree modeling, additional steps were required to complete the final land cover product. The extra steps used in the final classification were a combination of models created in ERDAS Imagine and manual edits. The four classes in urban and suburban areas were determined from the percent impervious mapping product (described in the next section). The threshold for the four classes is: (1) developed open space (imperviousness < 20%), (2) low-intensity developed (imperviousness from 20 - 49%), (3) medium intensity developed (imperviousness from 50 -79%), and (4) high-intensity developed (imperviousness > 79%). Other classes of forest and non-forest were combined with the urban classes to complete the land cover product. Finally visual inspection of the classification was made with areas/pixels that were wrongly classified delineated first as an "area of interest" (AOI), subsequently then limited manual editing performed to eliminate the classification error within the AOI.
The completed single pixel product was then generalized to a 1 acre (approximately 5 ETM+ 30 m pixel patch) minimum mapping unit product using a "smart eliminate" algorithm. This aggregation program subsumes pixels from the single pixel level to a 5-pixel patch using a queens algorithm at doubling intervals. The algorithm consults a weighting matrix to guide merging of cover types by similarity, resulting in a product that preserves land cover logic as much as possible.
Acquisition dates of Landsat ETM+ (TM) scenes used for land cover classification in zone 32 are as follows:
SPRING-
Index 1 for Path 26/Row 35 on 02/23/02 = Scene_ID 7026035000205450
Index 1 for Path 26/Row 36 on 02/23/02 = Scene_ID 7026036000205450
Index 1 for Path 26/Row 37 on 02/23/02 = Scene_ID 7026037000205450
Index 1 for Path 26/Row 38 on 02/23/02 = Scene_ID 7026038000205450
Index 4 for Path 27/Row 34 on 04/24/01 = Scene_ID 5027034000111410
Index 3 for Path 27/Row 35 on 04/03/02 = Scene_ID 7027035000209350
Index 3 for Path 27/Row 36 on 04/03/02 = Scene_ID 7027036000209350
Index 3 for Path 27/Row 37 on 04/03/02 = Scene_ID 7027037000209350
Index 2 for Path 27/Row 38 on 01/13/02 = Scene_ID 7027038000201350
Index 5 for Path 28/Row 35 on 03/09/02 = Scene_ID 7028035000206850
Index 5 for Path 28/Row 36 on 03/09/02 = Scene_ID 7028036000206850
Index 6 for Path 28/Row 37 on 02/02/01 = Scene_ID 7028037000103350
Index 7 for Path 29/Row 35 on 04/01/02 = Scene_ID 7029035000209150
LEAF ON (Summer)-
Index 3 for Path 26/Row 35 on 06/12/01 = Scene_ID 7026035000116350
Index 4 for Path 26/Row 36 on 06/15/02 = Scene_ID 7026036000216650
Index 4 for Path 26/Row 37 on 06/15/02 = Scene_ID 7026037000216650
Index 5 for Path 26/Row 38 on 07/19/00 = Scene_ID 5026038000020110
Index 1 for Path 27/Row 34 on 06/22/02 = Scene_ID 7027034000217350
Index 1 for Path 27/Row 35 on 06/22/02 = Scene_ID 7027035000217350
Index 1 for Path 27/Row 36 on 06/22/02 = Scene_ID 7027036000217350
Index 9 for Path 27/Row 36 on 07/21/01 = Scene_ID 7027036000120250
Index 2 for Path 27/Row 37 on 05/21/02 = Scene_ID 7027037000214150
Index 2 for Path 27/Row 38 on 05/21/02 = Scene_ID 7027038000214150
Index 6 for Path 28/Row 35 on 06/02/01 = Scene_ID 5028035000115310
Index 7 for Path 28/Row 36 on 06/10/01 = Scene_ID 7028036000116150
Index 7 for Path 28/Row 37 on 06/10/01 = Scene_ID 7028037000116150
Index 8 for Path 29/Row 35 on 05/19/02 = Scene_ID 7029035000213950
LEAF-OFF (Fall)-
Index 6 for Path 26/Row 35 on 10/13/99 = Scene_ID 7026035009928650
Index 6 for Path 26/Row 36 on 10/13/99 = Scene_ID 7026036009928650
Index 6 for Path 26/Row 37 on 10/13/99 = Scene_ID 7026037009928650
Index 7 for Path 26/Row 38 on 09/29/00 = Scene_ID 7026038000027350
Index 1 for Path 27/Row 34 on 10/25/01 = Scene_ID 7027034000129850
Index 1 for Path 27/Row 35 on 10/25/01 = Scene_ID 7027035000129850
Index 2 for Path 27/Row 36 on 10/20/99 = Scene_ID 7027036009929350
Index 1 for Path 27/Row 37 on 10/25/01 = Scene_ID 7027037000129850
Index 1 for Path 27/Row 38 on 10/25/01 = Scene_ID 7027038000129850
Index 3 for Path 28/Row 35 on 10/16/01 = Scene_ID 7028035000128950
Index 3 for Path 28/Row 36 on 10/16/01 = Scene_ID 7028036000128950
Index 4 for Path 28/Row 37 on 09/30/01 = Scene_ID 7028037000127350
Index 5 for Path 29/Row 35 on 10/23/01 = Scene_ID 7029035000129650
Landsat data and ancillary data used for the land cover prediction - -Data Type of DEM composed of 1 band of Continuous Variable Type. -Data Type of Slope composed of 1 band of Continuous Variable Type. -Data Type of Aspect composed of 1 band of Categorical Variable Type. -Data type of Position Index composed of 1 band of Continuous Variable Type.